Internal main

.gitignore

@@ -68,3 +68,14 @@ src/tests/e2e/evals/evaluation/rag_eval/examples/output/
 # UI test framework dependencies and results
 src/tests/node_modules
 test-results
+
+# Terraform 
+*.tfstate
+*.tfstate.backup
+.terraform/
+.terraform.lock.hcl
+crash.log
+override.tf
+override.tf.json
+*_override.tf
+*_override.tf.json

README.md

@@ -45,21 +45,27 @@ Document Summarization's pipeline architecture is available [here](./docs/images
    <img alt="ChatQnA Architecture" src="./docs/images/architecture_chatqna.svg" width="900">
 </div>
 
-# Table of Contents
+# Table of Contents <!-- omit from toc -->
+
 
 1. [Intel® AI for Enterprise RAG](#intel-ai-for-enterprise-rag)
    - [Why use Intel® AI for Enterprise RAG?](#why-use-intel-ai-for-enterprise-rag)
    - [Core Features](#core-features)
-3. [Requirements](#requirements)
+     - [Pipeline Architecture](#pipeline-architecture)
+2. [Requirements](#requirements)
    - [System Requirements](#system-requirements)
    - [Software Prerequisites](#software-prerequisites)
    - [Hardware Requirements](#hardware-requirements)
-      - [Deployment on Xeon only](#deployment-on-xeon-only)
-      - [Deployment on Xeon + Gaudi Accelerator](#deployment-on-xeon--gaudi-accelerator)
-4. [Getting Started](#getting-started)
-   - [Install a Kubernetes cluster (optional - if you don't have one)](#install-a-kubernetes-cluster-optional---if-you-dont-have-one)
-   - [Install infrastructure components (storage, operators, backup tools)](#install-infrastructure-components-storage-operators-backup-tools)
-   - [Deploy the Intel® AI for Enterprise RAG application on top of the prepared infrastructure](#deploy-the-intel-ai-for-enterprise-rag-application-on-top-of-the-prepared-infrastructure)
+     - [Deployment on Xeon only](#deployment-on-xeon-only)
+     - [Deployment on Xeon + Gaudi Accelerator](#deployment-on-xeon--gaudi-accelerator)
+3. [Getting Started](#getting-started)
+   - [Validate Hardware Requirements](#validate-hardware-requirements)
+   - [Intel Enterprise RAG Deployment - Standalone](#intel-enterprise-rag-deployment---standalone)
+     - [Install a Kubernetes cluster (optional - if you don't have one)](#install-a-kubernetes-cluster-optional---if-you-dont-have-one)
+     - [Install infrastructure components (storage, operators, backup tools)](#install-infrastructure-components-storage-operators-backup-tools)
+     - [Deploy the Intel® AI for Enterprise RAG application on top of the prepared infrastructure](#deploy-the-intel-ai-for-enterprise-rag-application-on-top-of-the-prepared-infrastructure)
+4. [Intel AI Enterprise RAG Deployment - Partner Solutions](#intel-ai-enterprise-rag-deployment---partner-solutions)
+   - [Nutanix AI & Intel® AI for Enterprise RAG](#nutanix-ai--intel-ai-for-enterprise-rag)
 5. [Documentation](#documentation)
 6. [Support](#support)
 7. [Publications](#publications)
@@ -138,11 +144,13 @@ ansible-playbook playbooks/validate.yaml --tags hardware -i inventory/test-clust
 > [!NOTE]
 > If this is a Gaudi deployment, add the additional flag `-e is_gaudi_platform=true`
 
-## Install a Kubernetes cluster (optional - if you don't have one)
+## Intel AI Enterprise RAG Deployment - Standalone
+
+### Install a Kubernetes cluster (optional - if you don't have one)
 
 Intel® AI for Enterprise RAG offers ansible automation for creating a K8s cluster. If you want to set up a K8s cluster, follow the [Cluster Deployment Guide](docs/cluster_deployment_guide.md).
 
-## Install infrastructure components (storage, operators, backup tools)
+### Install infrastructure components (storage, operators, backup tools)
 
 The Intel® AI for Enterprise RAG repository offers installation of additional infrastructure components on the deployed K8s cluster:
 - **Gaudi_operator** - dedicated for K8s clusters with nodes that use Gaudi AI accelerators
@@ -151,10 +159,16 @@ The Intel® AI for Enterprise RAG repository offers installation of additional i
 
 If your K8s cluster requires installing any of these tools, please follow the [Infrastructure Components Guide](docs/infrastructure_components_guide.md).
 
-## Deploy the Intel® AI for Enterprise RAG application on top of the prepared infrastructure
+### Deploy the Intel® AI for Enterprise RAG application on top of the prepared infrastructure
 
 Once you have a K8s cluster with all infrastructure components installed, you can install the Intel® AI for Enterprise RAG application on top of it. Please follow the [Application Deployment Guide](docs/application_deployment_guide.md).
 
+# Intel AI Enterprise RAG Deployment - Partner Solutions
+
+## Nutanix AI & Intel® AI for Enterprise RAG
+
+Follow documentation to deploy Nutanix AI with Intel® AI for Enterprise RAG using the [Nutanix AI Deployment Guide](docs/nutanix/README.md).
+
 # Documentation
 
 Refer to [deployment/README.md](deployment/README.md) or [docs](docs/) for more detailed deployment guide or in-depth instructions on Intel® AI for Enterprise RAG components.
@@ -166,6 +180,8 @@ Submit questions, feature requests, and bug reports on the GitHub Issues page.
 # Publications
 
 Feel free to checkout articles about Intel® AI for Enterprise RAG:
+* [Securing Enterprise RAG Deployments](https://www.intel.com/content/www/us/en/content-details/870124/securing-enterprise-rag-deployments.html)
+* [Document Summarization: Transforming Enterprise Content with Intel® AI for Enterprise RAG](https://community.intel.com/t5/Blogs/Tech-Innovation/Artificial-Intelligence-AI/Document-Summarization-Transforming-Enterprise-Content-with/post/1728252)
 * [Scaling Intel® AI for Enterprise RAG Performance: 64-Core vs 96-Core Intel® Xeon®](https://community.intel.com/t5/Blogs/Tech-Innovation/Artificial-Intelligence-AI/Scaling-Intel-AI-for-Enterprise-RAG-Performance-64-Core-vs-96/post/1723234)
 * [Comprehensive Analysis: Intel® AI for Enterprise RAG Performance](https://community.intel.com/t5/Blogs/Tech-Innovation/Artificial-Intelligence-AI/Comprehensive-Analysis-Intel-AI-for-Enterprise-RAG-Performance/post/1723226)
 * [Monitoring and Debugging RAG Systems in Production](https://community.intel.com/t5/Blogs/Tech-Innovation/Artificial-Intelligence-AI/Monitoring-and-Debugging-RAG-Systems-in-Production/post/1720292)

deployment/.gitignore

@@ -0,0 +1,3 @@
+upgrade/metadata/*
+upgrade/reports/*
+components/velero/charts/*

deployment/README.md

@@ -82,6 +82,9 @@ The Intel® AI for Enterprise RAG repository offers installation of additional i
 
 If your K8s cluster requires installing any of these tools, follow the [Infrastructure Components Guide](../docs/infrastructure_components_guide.md).
 
+> [!NOTE]
+> The `pre-install` tag automatically preconfigures system limits (such as file descriptors, process limits, and kernel parameters) on cluster nodes to ensure optimal performance for Enterprise RAG workloads. These configurations are applied before the main installation process.
+
 ## Deploy the Intel® AI for Enterprise RAG application on top of the prepared infrastructure
 
 Once you have a K8s cluster with all infrastructure components installed, you can install the Intel® AI for Enterprise RAG application on top of it. Follow the [Application Deployment Guide](../docs/application_deployment_guide.md).

deployment/components/apisix-routes/Chart.yaml

@@ -1,4 +1,7 @@
 apiVersion: v2
 name: auth-apisix-crds
 description: A Helm chart with APISIX CRDs for backend services with authentication
-version: 2.0.0
+version: 2.0.2
+appVersion: "2.0.1"
+annotations:
+  app.kubernetes.io/part-of: ERAG

deployment/components/apisix/Chart.yaml

@@ -1,8 +1,11 @@
 apiVersion: v2
 name: auth-apisix
 description: A Helm chart for installing a specific version of APISIX API gateway and APISIX ingress controller
-version: 2.0.0
-appVersion: "2.0.0"
+version: 2.0.2
+appVersion: "2.0.1"
+annotations:
+  app.kubernetes.io/part-of: ERAG
+
 dependencies:
   - name: apisix
     version: 2.10.0

deployment/components/chat_history/Chart.lock

@@ -1,6 +1,6 @@
 dependencies:
 - name: ferretdb
   repository: file://../ferretdb
-  version: 0.1.4
-digest: sha256:6c5b2907f7e2b972862db959001d3dc134a7145225709c5a8ccf055ecac7fe53
-generated: "2025-10-15T09:52:29.798192647-07:00"
+  version: 0.1.5
+digest: sha256:a51244a409b5e3ae2aae8181354acf88bb3f2aa8e46f593d2c10c95328673c01
+generated: "2025-12-09T13:57:32.412736756+01:00"

deployment/components/chat_history/Chart.yaml

@@ -4,13 +4,13 @@
 apiVersion: v2
 name: chat-history
 description: Chat History Helm chart
-
 type: application
-
-version: 0.1.0
-appVersion: "1.16.0"
+version: 0.1.2
+appVersion: "2.0.1"
+annotations:
+  app.kubernetes.io/part-of: ERAG
 
 dependencies:
   - name: ferretdb
-    version: "0.1.4"
+    version: "*"
     repository: "file://../ferretdb"

deployment/components/edp/Chart.lock

@@ -4,9 +4,9 @@ dependencies:
   version: 14.10.3
 - name: edp-redis
   repository: file://charts/edp-redis
-  version: 1.0.0
+  version: 1.0.1
 - name: postgresql
   repository: file://../postgresql
-  version: 0.1.0
-digest: sha256:985d9da111b8309178248b9dcbc5fcab5a51c12a1b12eda30bf934d8632db14c
-generated: "2025-11-05T12:07:28.356959671-08:00"
+  version: 0.1.2
+digest: sha256:1f725f474b78af7321073a7b994ea78df8dba3ffbfdb4e10fb4ce14f1ff1c23d
+generated: "2025-12-09T13:57:42.096648941+01:00"

deployment/components/edp/Chart.yaml

@@ -4,21 +4,20 @@
 apiVersion: v2
 name: helm-edp
 description: Enchanced dataprep pipeline chart
-
 type: application
-
-version: 0.1.0
-
-appVersion: "1.16.0"
+version: 0.1.2
+appVersion: "2.0.1"
+annotations:
+  app.kubernetes.io/part-of: ERAG
 
 dependencies:
   - name: minio
     version: 14.10.3
     repository: https://charts.bitnami.com/bitnami
     condition: minio.enabled
   - name: edp-redis
-    version: 1.0.0
+    version: "*"
     repository: file://charts/edp-redis
   - name: postgresql
-    version: 0.1.0
+    version: "*"
     repository: file://../postgresql

deployment/components/edp/charts/edp-redis/Chart.yaml

@@ -2,5 +2,7 @@ apiVersion: v2
 name: edp-redis
 description: Standalone Redis 8.2.2 for EDP
 type: application
-version: 1.0.0
-appVersion: "8.2.2"
+version: 1.0.1
+appVersion: "2.0.1"
+annotations:
+  app.kubernetes.io/part-of: ERAG

deployment/components/edp/templates/backend/backend-deployment.yaml

@@ -14,10 +14,11 @@ spec:
       {{- include "helm-edp.backend.selectorLabels" . | nindent 6 }}
   template:
     metadata:
-      {{- with .Values.podAnnotations }}
       annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }}
+        {{- with .Values.podAnnotations }}
         {{- toYaml . | nindent 8 }}
-      {{- end }}
+        {{- end }}
       {{- include "manifest.podLabels" (list .Values.backend.nameOverride .) | nindent 6 }}
       {{- include "manifest.tdx.annotations" (list .Values.backend.nameOverride .) | nindent 6 }}
     spec:

deployment/components/edp/templates/celery/celery-deployment.yaml

@@ -14,10 +14,11 @@ spec:
       {{- include "helm-edp.celery.selectorLabels" . | nindent 6 }}
   template:
     metadata:
-      {{- with .Values.podAnnotations }}
       annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }}
+        {{- with .Values.podAnnotations }}
         {{- toYaml . | nindent 8 }}
-      {{- end }}
+        {{- end }}
       {{- include "manifest.podLabels" (list .Values.celery.nameOverride .) | nindent 6 }}
       {{- include "manifest.tdx.annotations" (list .Values.celery.nameOverride .) | nindent 6 }}
     spec:

deployment/components/edp/templates/configmap.yaml

@@ -5,7 +5,7 @@ apiVersion: v1
 kind: ConfigMap
 metadata:
   name: edp-configmap
-  namespace: edp
+  namespace: {{ .Release.Namespace }}
 data:
   HIERARCHICAL_DATAPREP_ENDPOINT: {{ if .Values.hierarchicalDataprep.enabled }}{{ print "http://" .Values.hierarchicalDataprep.nameOverride ":9399/v1/hierarchical_dataprep" | quote }}{{ else }}""{{ end }}
   TEXT_EXTRACTOR_ENDPOINT: {{ if not .Values.hierarchicalDataprep.enabled }}{{ print "http://" .Values.textExtractor.nameOverride ":9398/v1/text_extractor" | quote }}{{ else }}""{{ end }}
@@ -22,3 +22,29 @@ data:
   DPGUARD_ENABLED: {{ .Values.dpguard.enabled | quote }}
   FINGERPRINT_ENDPOINT: "http://fingerprint-svc.fingerprint.svc:6012/v1/system_fingerprint/append_arguments"
   PRESIGNED_URL_CREDENTIALS_SYSTEM_FALLBACK: {{ .Values.presignedUrlCredentialsSystemFallback | quote }}
+  {{- /* Query TorchServe configuration from chatqa namespace */ -}}
+  {{- $torchserveReplicas := 1 }}
+  {{- $torchserveBatchSize := 32 }}
+  {{- $torchserveMaxWorkers := 4 }}
+  {{- /* Lookup TorchServe deployment */ -}}
+  {{- $torchserveDeployments := lookup "apps/v1" "Deployment" "chatqa" "" }}
+  {{- if $torchserveDeployments }}
+    {{- range $torchserveDeployments.items }}
+      {{- if hasPrefix "torchserve-embedding-svc-" .metadata.name }}
+        {{- $torchserveReplicas = .spec.replicas }}
+      {{- end }}
+    {{- end }}
+  {{- end }}
+  {{- /* Lookup TorchServe ConfigMap for batch size and workers */ -}}
+  {{- $torchserveConfigMap := lookup "v1" "ConfigMap" "chatqa" "torchserve-embedding-config" }}
+  {{- if $torchserveConfigMap }}
+    {{- if $torchserveConfigMap.data.TORCHSERVE_BATCH_SIZE }}
+      {{- $torchserveBatchSize = $torchserveConfigMap.data.TORCHSERVE_BATCH_SIZE | int }}
+    {{- end }}
+    {{- if $torchserveConfigMap.data.TORCHSERVE_MAX_WORKERS }}
+      {{- $torchserveMaxWorkers = $torchserveConfigMap.data.TORCHSERVE_MAX_WORKERS | int }}
+    {{- end }}
+  {{- end }}
+  {{- /* Calculate CELERY_BATCH_SIZE = replicas × max_workers × batch_size */ -}}
+  {{- $celeryBatchSize := mul (mul $torchserveReplicas $torchserveMaxWorkers) $torchserveBatchSize }}
+  CELERY_BATCH_SIZE: {{ $celeryBatchSize | quote }}

deployment/components/edp/templates/flower/flower-deployment.yaml

@@ -15,10 +15,11 @@ spec:
       {{- include "helm-edp.flower.selectorLabels" . | nindent 6 }}
   template:
     metadata:
-      {{- with .Values.podAnnotations }}
       annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }}
+        {{- with .Values.podAnnotations }}
         {{- toYaml . | nindent 8 }}
-      {{- end }}
+        {{- end }}
       {{- include "manifest.podLabels" (list .Values.flower.nameOverride .) | nindent 6 }}
       {{- include "manifest.tdx.annotations" (list .Values.flower.nameOverride .) | nindent 6 }}
     spec:

deployment/components/edp/templates/ingestion/ingestion-deployment.yaml

@@ -14,10 +14,11 @@ spec:
       {{- include "helm-edp.ingestion.selectorLabels" . | nindent 6 }}
   template:
     metadata:
-      {{- with .Values.podAnnotations }}
       annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/ingestion/ingestion-configmap.yaml") . | sha256sum }}
+        {{- with .Values.podAnnotations }}
         {{- toYaml . | nindent 8 }}
-      {{- end }}
+        {{- end }}
       {{- include "manifest.podLabels" (list .Values.ingestion.nameOverride .) | nindent 6 }}
       {{- include "manifest.tdx.annotations" (list .Values.ingestion.nameOverride .) | nindent 6 }}
     spec:

deployment/components/edp/templates/textCompression/text-compression-deployment.yaml

@@ -15,10 +15,11 @@ spec:
       {{- include "helm-edp.textCompression.selectorLabels" . | nindent 6 }}
   template:
     metadata:
-      {{- with .Values.podAnnotations }}
       annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/textCompression/text-compression-configmap.yaml") . | sha256sum }}
+        {{- with .Values.podAnnotations }}
         {{- toYaml . | nindent 8 }}
-      {{- end }}
+        {{- end }}
       {{- include "manifest.podLabels" (list .Values.textCompression.nameOverride .) | nindent 6 }}
       {{- include "manifest.tdx.annotations" (list .Values.textCompression.nameOverride .) | nindent 6 }}
     spec:

deployment/components/edp/templates/textExtractor/text-extractor-deployment.yaml

@@ -15,10 +15,11 @@ spec:
       {{- include "helm-edp.textExtractor.selectorLabels" . | nindent 6 }}
   template:
     metadata:
-      {{- with .Values.podAnnotations }}
       annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }}
+        {{- with .Values.podAnnotations }}
         {{- toYaml . | nindent 8 }}
-      {{- end }}
+        {{- end }}
       {{- include "manifest.podLabels" (list .Values.textExtractor.nameOverride .) | nindent 6 }}
       {{- include "manifest.tdx.annotations" (list .Values.textExtractor.nameOverride .) | nindent 6 }}
     spec:

deployment/components/edp/templates/textSplitter/text-splitter-deployment.yaml

@@ -15,10 +15,11 @@ spec:
       {{- include "helm-edp.textSplitter.selectorLabels" . | nindent 6 }}
   template:
     metadata:
-      {{- with .Values.podAnnotations }}
       annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/textSplitter/text-splitter-configmap.yaml") . | sha256sum }}
+        {{- with .Values.podAnnotations }}
         {{- toYaml . | nindent 8 }}
-      {{- end }}
+        {{- end }}
       {{- include "manifest.podLabels" (list .Values.textSplitter.nameOverride .) | nindent 6 }}
       {{- include "manifest.tdx.annotations" (list .Values.textSplitter.nameOverride .) | nindent 6 }}
     spec: